INDEX

Explanations

references to "half" or phrases related to partiality

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/dataTables

-0.15

esti

-0.15

las

-0.14

lint

-0.14

essim

-0.14

eten

-0.14

 Levels

-0.14

lac

-0.14

ç

-0.13

POSITIVE LOGITS

 dozen

0.26

moon

0.20

/full

0.20

weep

0.17

Ø§ÙĨ

0.17

-half

0.16

 Moon

0.16

enger

0.15

ittings

0.15

 moon

0.15

Activations Density 0.051%

references to "half" or phrases related to partiality

No Comments

No Known Activations